# MCP CPG Knowledge Graph MCP server

BPC Agentic Commerce Infra

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-greencore-solutions-cpg-knowledge-graph
- Repository: https://github.com/greencore-solutions/mcp-cpg-gtin
- Website: https://cpgknowledgegraph.ai

## Install
- Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://mcp.cpgknowledgegraph.ai/mcp

## Tools
- resolve_gtin - Resolve a GTIN to its procurement readiness signal. Zero-pads input to 14 digits. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- check_eligibility - Check whether a GTIN can ship to a specific retailer banner in a country. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- get_signal_chain - Return the full ACM-68000 signal chain for a GTIN (zero-pads to 14). Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- count_gtin_coverage - Global coverage statistics: GTINs, nodes, makers (supply), retailers (demand). Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- resolve_scope - GSC Scoped Agents Registry — 1,000,000 scoped identities under SM-ECO-10060. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- list_nodes - The 49 sovereign nodes (the spine) — each with its GS1 GTIN and CLEAN per-node
maker (supply) and retailer (demand) counts (separate subqueries, never summed). Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- resolve_node - Resolve one node: its GS1 license + its makers (supply) + its retailers (demand). Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- find_makers - Global cross-node maker (supply) search. Filter by segment / region / node / has_website. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- find_retailers - Global cross-node retailer (demand) search. Filter by region / node / parent_banner. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- node_market - Supply↔demand bridge for ONE jurisdiction: makers (supply) and retailers (demand)
as two separate counts (never summed), plus the same-node potential bridge pairs. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- list_sku_types - SPARKS taxonomy: the 84 standing BPC product-type codes the graph is structured
on. Validate a type against this before a typed query. (BRAND is a tier, not a type.) Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- list_brands_by_node - SPARKS depth surface: the distinct brands SPARKS covers in a sovereign market.
Answers 'what brands do you know in [node]'. Coverage only — no pack/size values. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- get_kernel - SPARKS completeness tier for a brand in a market:
  100 = resolvable (a real pack/size record is held) . 8 = registered (brand known,
  pack/size pending) . 'floor' = STANDARD default (no brand-specific record).
Returns the stored tier flag — do NOT compute a score. Never returns a pack/size. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp
- resolve_sparks - Two-branch SPARKS resolver (zero-pads GTIN to 14).
  Branch A  GSC Territory/License GTIN (990832300xxx) -> FULL license record (public).
  Branch B  any third-party BPC GTIN -> GATED proof {recognized, region_node,
            kernel_available}; the pack/size VALUE is NEVER returned. Route to Navigator.
Brand match is fail-closed (normalized exact match); uncertainty -> recognized:false. Endpoint: https://mcp.cpgknowledgegraph.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.greencore-solutions
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 19, 2026
- Source: https://registry.modelcontextprotocol.io